ICLR 2026 论文列表

Large language models (LLMs) have shown strong performance in single-language code generation, but how well they produce cross-programming-language (CPL) interoperating code, which is widely used in cross-platform and complex software systems, remains underexplored. Therefore, a benchmark for evaluating CPL interaction code generation is essential. However, Constructing such a benchmark is challenging owing to sparse interoperating code in real-world multi-programming-language projects, diverse Inter-process Communication (IPC) mechanisms, vast Foreign Function Interface (FFI) language pairs, and the difficulty of evaluation. To address this gap, we introduce CrossPL, the first benchmark for systematically assessing LLM performance of CPL code generation across two primary interoperation modes and 2534 tasks, specifically 1,982 IPC tasks spanning six languages and 522 Python–C FFI tasks. Its construction involved a review of CPL documentation, 156 finite state machines, and analysis of 19,169 multi-language GitHub repositories. Two LLM-based workflows are designed for automating the benchmark construction and evaluation, and assess 20 state-of-the-art LLMs. Results reveal clear limitations: the best model achieves only 19.5\% Pass@1 and 26.46\% Pass@5 on the FFI subset, in sharp contrast to the strong performance of these models on single-language benchmarks. These findings underscore the urgent need for improving LLMs regarding CPL interoperating code generation. The benchmark and code are available at https://anonymous.4open.science/r/crosspl-2814/.

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models (MLLMs), yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection. Such approaches neglect fine-grained links among visual inputs, temporal dynamics, and linguistic outputs, limiting both accuracy and interpretability. We propose Video-KTR, a modality-aware policy shaping framework that performs selective, token-level RL by combining three attribution signals: (1) visual-aware tokens identified via counterfactual masking to reveal perceptual dependence; (2) temporal-aware tokens detected through frame shuffling to expose causal and temporal sensitivity; and (3) high-entropy tokens signaling predictive uncertainty. By reinforcing only the union of key tokens, Video-KTR focuses learning on semantically informative, modality-sensitive content while filtering out low-value tokens. Across five challenging benchmarks, Video-KTR achieves state-of-the-art or highly competitive results—42.7% on Video-Holmes, surpassing GPT-4o—with consistent gains on both reasoning-centric and general video understanding tasks. Ablation studies verify the complementary roles of the attribution signals and the robustness of targeted token-level updates. Overall, Video-KTR improves accuracy and interpretability, offering a simple, drop-in extension to RL for complex video reasoning.

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal generative model that integrates a coarse 1-NFE MeanFlow transport with a subsequent tailored noise-injection refinement step. RMFlow approximates the average velocity of the flow path using a neural network trained with a new loss function that balances minimizing the Wasserstein distance between probability paths and maximizing sample likelihood. RMFlow achieves near state-of-the-art results on text-to-image, context-to-molecule, and time-series generation using only 1-NFE, at a computational cost comparable to the baseline MeanFlows.

We introduce SEINT, a novel Special Euclidean group-Invariant (SE(\emph{p})) metric for comparing probability distributions on $p$-dimensional measured Banach spaces. Existing SE(\emph{p})-invariant alignment methods often face high computational costs or lack metric guarantees. To overcome these limitations, we develop a polar transport discrepancy combined with distance convolution to extract SE(\emph{p})-invariant representations. These representations are then used to compute the alignment between two distributions via optimal transport. Theoretically, we prove that SEINT is a well-defined metric on the space of isometry classes of normed vector spaces. Beyond its inherent SE(\emph{p})-invariance, SEINT also supports cross-space distribution comparison. Computationally, SEINT aligns two samples of size $n$ with a complexity of just $\mathcal{O}(n\log n)$ to $\mathcal{O}(n^2)$. Extensive experiments validate its advantages: As a robust metric, it outperforms or matches existing SE(\emph{p})-invariant methods in classification and cross-space tasks under isometries. As a regularizer, it greatly enhances molecular generation performance across both pre-training and fine-tuning tasks, achieving state-of-the-art (SOTA) results on key benchmarks.

Diffusion models have recently become the dominant paradigm for image generation, yet existing systems struggle to interpret and follow numeric instructions for adjusting semantic attributes. In real-world creative scenarios, especially when precise control over aesthetic attributes is required, current methods fail to provide such controllability. This limitation partly arises from the subjective and context-dependent nature of aesthetic judgments, but more fundamentally stems from the fact that current text encoders are designed for discrete tokens rather than continuous values. Meanwhile, efforts on aesthetic alignment, often leveraging reinforcement learning, direct preference optimization, or architectural modifications, primarily align models with a global notion of human preference. While these approaches improve user experience, they overlook the multifaceted and compositional nature of aesthetics, underscoring the need for explicit disentanglement and independent control of aesthetic attributes. To address this gap, we introduce AttriCtrl, a lightweight framework for continuous aesthetic intensity control in diffusion models. It first decomposes relevant aesthetic attributes, then quantifies them through a hybrid strategy that maps both concrete and abstract dimensions onto a unified $[0,1]$ scale. A plug-and-play value encoder is then used to transform user-specified values into model-interpretable embeddings for controllable generation. Experiments show that AttriCtrl achieves accurate and continuous control over both single and multiple aesthetic attributes, significantly enhancing personalization and diversity. Crucially, it is implemented as a lightweight adapter while keeping the diffusion model frozen, ensuring seamless integration with existing frameworks such as ControlNet at negligible computational cost.

Pretrained medical foundation models (FMs) have shown strong generalization across diverse imaging tasks, such as disease classification in radiology and tumor grading in histopathology. While recent advances in parameter-efficient finetuning have enabled effective adaptation of FMs to downstream tasks, these approaches are typically designed for a single modality. In contrast, many clinical workflows rely on joint diagnosis from heterogeneous domains, such as radiology and pathology, where fully leveraging the representation capacity of multiple FMs remains an open challenge. To address this gap, we propose Concept Tuning and Fusing (CTF), a parameter-efficient framework that uses clinically grounded concepts as a shared semantic interface to enable cross-modal co-adaptation before fusion. By incorporating task-specific concepts that are relevant across modalities, CTF aligns radiology and pathology representations, thereby enhancing their complementarity and enabling interpretation. We further design a Global–Context–Shared Prompt (GCSP) mechanism, which employs a small set of learnable tokens to capture domain-specific priors, shared patient-level information, and cross-domain context. The resulting concept alignment scores from each modality are then fused to produce a final prediction. Extensive experiments demonstrate that CTF outperforms strong unimodal, latent-fusion, and adapter-based baselines (e.g., AUC 0.903 on TCGA-GBMLGG). Notably, CTF achieves these gains without finetuning the full FMs, requiring only 0.15\% additional parameters, thus highlighting the effectiveness of concept-based multimodal co-adaptation. Our code is anonymously available at: https://anonymous.4open.science/r/CTF-27C2.

Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data, demonstrating remarkable success in many real-world applications such as complex biological network analysis, neuroscientific analysis, and social network analysis. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While numerous methods have been proposed to address this challenge, they primarily focus on architectural designs without directly targeting the root cause of the heterophily problem. These approaches still perform even worse than the simplest MLPs on challenging heterophilic datasets. For instance, our experiments show that 23 latest GNNs still fall behind the MLP on the Actor dataset. This critical challenge calls for an innovative approach to addressing graph heterophily beyond architectural designs. To bridge this gap, we propose and study a new and unexplored paradigm: directly increasing the graph homophily via a carefully designed graph transformation. In this work, we present a simple yet effective framework called Graph Homophily Booster (GRAPHITE) to address graph heterophily. To the best of our knowledge, this work is the first method that explicitly transforms the graph to directly improve the graph homophily. Stemmed from the exact definition of homophily, our proposed GRAPHITE creates feature nodes to facilitate homophilic message passing between nodes that share similar features. Furthermore, we both theoretically and empirically show that our proposed GRAPHITE significantly increases the homophily of originally heterophilic graphs, with only a slight increase in the graph size. Extensive experiments on challenging datasets demonstrate that our proposed GRAPHITE significantly outperforms state-of-the-art methods on heterophilic graphs while achieving comparable accuracy with state-of-the-art methods on homophilic graphs. Furthermore, our proposed graph transformation alone can already enhance the performance of homophilic GNNs on heterophilic graphs, even though they were not originally designed for heterophilic graphs. Our code is publicly available at https://github.com/q-rz/ICLR26-GRAPHITE .

Existing AI-based film generation systems can generate high-quality videos, but struggle to design expressive camera language and establish cinematic rhythm. This deficiency leads to templated visuals and unengaging narratives. To address these limitations, we introduce FilMaster, an end-to-end automated film generation system that integrates real-world cinematic principles to generate professional-grade, editable films. Inspired by professional filmmaking, FilMaster is built on two key cinematic principles: (1) camera language design by learning cinematography from extensive real-world film references, and (2) cinematic rhythm by emulating professional post-production workflows. For camera language, our Multi-shot Synergized Camera Language Design module introduces a novel scene-level Retrieval-Augmented Generation (RAG) framework. Unlike shot-level RAG which retrieves references independently and often leads to visual incoherence, our approach treats an entire scene, comprising multiple shots with a shared spatio-temporal context and narrative objective, as a single, unified query. This holistic query retrieves a consistent set of semantically similar shots with cinematic techniques from a large corpus of 440,000 real film clips. These references then guide an LLM to synergistically plan coherent and expressive camera language for all shots within that scene. To achieve cinematic rhythm, our Audience-Aware Cinematic Rhythm Control module emulates professional post-production, featuring a Rough Cut assembly followed by a Fine Cut process that uses simulated audience feedback to optimize the integration of video and sound for cinematic rhythm. Extensive experiments show superior performance in camera language and cinematic rhythm, paving the way for generative AI in professional filmmaking.

Rigorous testing of autonomous robots, such as self-driving vehicles, is essential to ensure their safety in real-world deployments. This requires building high-fidelity simulators to test scenarios beyond those that can be safely or exhaustively collected in the real-world. Existing neural rendering methods based on NeRF and 3DGS hold promise but suffer from low rendering speeds or can only render pinhole camera models, hindering their suitability to applications that commonly require high-distortion lenses and LiDAR data. Multi-sensor simulation poses additional challenges as existing methods handle cross-sensor inconsistencies by favoring the quality of one modality at the expense of others. To overcome these limitations, we propose SimULi, the first method capable of rendering arbitrary camera models and LiDAR data in real-time. Our method extends 3DGUT, which natively supports complex camera models, with LiDAR support, via an automated tiling strategy for arbitrary spinning LiDAR models and ray-based culling. To address cross-sensor inconsistencies, we design a factorized 3D Gaussian representation and anchoring strategy that reduces mean camera and depth error by up to 40% compared to existing methods. SimULi renders 10-20$\times$ faster than ray tracing approaches and 1.5-14$\times$ faster than prior rasterization-based work (and handles a wider range of camera models). When evaluated on two widely benchmarked autonomous driving datasets, SimULi matches or exceeds the fidelity of existing state-of-the-art methods across numerous camera and LiDAR metrics.

This paper studies the expressive power of linear attention layers for in-context learning (ICL) of linear dynamical systems (LDS). We consider training on sequences of inexact observations produced by noise-corrupted LDSs, with all perturbations being Gaussian; importantly, we study the non-i.i.d. setting as it is closer to real-world scenarios. We provide the optimal weight construction for a single linear-attention layer and show its equivalence to one step of Gradient Descent relative to an autoregression objective of window size one. Guided by experiments, we uncover a relation to the Preconditioned Conjugate Gradient method for larger window sizes. We back our findings with numerical evidence. These results add to the existing understanding of transformers' expressivity as in-context learners, and offer plausible hypotheses for experimental observations whereby they compete with Kalman filters --- the optimal model-dependent learners for this setting.

Signal integrity issues present significant challenges in modern integrated circuit (IC) design, as crosstalk-induced delay variation and transient glitches caused by capacitive coupling among interconnects can severely impact IC functional correctness. Although circuit simulators like SPICE can deliver accurate signal integrity analysis, their computational cost becomes prohibitive for large-scale designs. In this paper, we propose Si-GT, a novel transformer-based model for fast and accurate signal integrity analysis in IC interconnects. Our model elaborates three key designs: (1) virtual NET token to encode net-specific signal characteristics and serve as net-wise representation, (2) mesh pattern encoding to embed high-order mesh structures at each node while distinguishing uncoupled wire segments, and (3) intra-inter net (IIN) attention mechanism to capture structures of signal propagation path and coupling connections. To support model training and evaluation, we construct the first interconnect signal integrity dataset comprising 200k delay examples and 187k glitch examples using SPICE simulations as the golden reference. Our experiments show that our Si-GT surpasses state-of-the-art graph neural network and graph transformer baselines with substantially reduced computation compared to SPICE, offering a scalable and effective solution for interconnect signal integrity analysis in IC design verification.

Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding capacity. However, the scarcity of multimodal aesthetic reasoning data and the inherently subjective nature of aesthetic judgment make it difficult for MLLMs to generate accurate aesthetic judgments with interpretable rationales. To this end, we propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL). Concretely, Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data used for cold-start. After teaching the model to generate structured explanations prior to scoring, we then employ the Relative-Absolute Policy Optimization (RAPO), a novel RL algorithm that jointly optimizes absolute score regression and relative ranking order, improving both per-image accuracy and cross-image preference judgments. Aes-R1 enables MLLMs to generate grounded explanations alongside faithful scores, thereby enhancing aesthetic scoring and reasoning in a unified framework. Extensive experiments demonstrate that Aes-R1 improves the backbone’s average PLCC/SRCC by 47.9%/34.8%, surpassing state-of-the-art baselines of similar size. More ablation studies validate Aes-R1's robust generalization under limited supervision and in out-of-distribution scenarios.

State-of-the-art models for code representation, such as GraphCodeBERT, embed the hierarchical structure of source code into Euclidean space. This approach can lead to significant representation distortion, especially when embedding deep or highly branched hierarchies,limiting the models' ability to capture deep program semantics. We argue that the natural geometry for code is hyperbolic, as its exponential volume growth perfectly matches the tree-like structure of a code's Abstract Syntax Tree (AST), enabling low-distortion hierarchical embeddings. We introduce {HypeCodeNet}, a geometric deep learning framework that operates natively in hyperbolic space. Formulated in the numerically stable Lorentz model, its manifold-aware components include a hyperbolic embedding layer, a tangent space message-passing mechanism, and a geodesic-based attention module. On code clone detection, code completion, and link prediction, HypeCodeNet significantly outperforms existing Euclidean models, especially on tasks requiring deep structural understanding. Our work suggests that hyperbolic geometry offers a geometrically sound foundation for code representation, establishing hyperbolic geometry as a key to unlocking the structured semantics of code.

Ensuring factuality is essential for the safe use of Large Language Models (LLMs) in high-stakes domains such as medicine and law. Conformal inference provides distribution-free guarantees, but existing approaches are either overly conservative, discarding many true-claims, or rely on adaptive error rates and simple linear models that fail to capture complex group structures. To address these challenges, we reformulate conformal inference in a multiplicative filtering setting, modeling factuality as a product of claim-level scores. Our method, Multi-LLM Adaptive Conformal Inference MACI, leverages ensembles to produce more accurate factuality scores, which in our experiments led to higher retention, while validity is preserved through group-conditional calibration. Experiments show that MACI consistently achieves user-specified coverage with substantially higher retention and lower time cost than baselines. Our anonymized repository is available at https://github.com/MLAI-Yonsei/MACI.git

Text-to-image (T2I) diffusion models achieve impressive photorealism by training on large-scale web data, but models inherit cultural biases and fail to depict underrepresented regions faithfully. Existing cultural benchmarks focus mainly on object-centric categories (e.g., food, attire, and architecture), overlooking the social and daily activities that more clearly reflect cultural norms. Few metrics exist for measuring cultural faithfulness. We introduce CULTIVate, a benchmark for evaluating T2I models on cross-cultural activities (e.g., greetings, dining, games, traditional dances, and cultural celebrations). CULTIVate spans 16 countries with 576 prompts and more than 19,000 images, and provides an explainable descriptor-based evaluation framework across multiple cultural dimensions, including background, attire, objects, and interactions. We propose four metrics to measure cultural alignment, hallucination, exaggerated elements, and diversity. Our findings reveal systematic disparities: models perform better for global north countries than for the global south, with distinct failure modes across T2I systems. Human studies confirm that our metrics correlate more strongly with human judgments than existing text–image measures.

Learning the dynamic causal structure is a difficult challenge in discovering causality from time series. Most existing studies rely on distributional or structural invariance to uncover the underlying causal dynamics, assuming stationary or partially stationary causality, which frequently conflicts with complex causal relationships in the real world. This boosts temporal causal discovery to encompass fully dynamic causality, where both instantaneous and lagged causal dependencies may change over time, bringing significant challenges to the efficiency and stability of causal discovery. To tackle these challenges, we introduce DyCausal, a dynamic causal structure learning framework that leverages convolutional networks to effectively model causal structures within coarse-grained time windows, and introduces linear interpolation to refine causal structures to each time step and recover time-varying causal graphs. In addition, we propose an acyclic constraint based on matrix norm scaling. It is more stable both theoretically and empirically, and constrains loops in dynamic causal structures with improved efficiency. Evaluations on both synthetic and real-world datasets prove that DyCausal significantly outperforms existing methods and identifies fully dynamic causal structures from coarse to fine.

Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely challenging to assign credit when training LLM agents that serve as a policy. Recent work attempts to integrate process supervision into RL but suffers from biased annotation, reward hacking, high-variance from overly fine-grained rewards or failures when state overlap is rare. We therefore introduce implicit step rewards for agentic RL (**iStar**), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms without relying on additional rollouts or explicit step labels. Particularly, we alternatively optimize an implicit process reward model (PRM) with the policy model to generate step rewards for each action via a multi-turn DPO objective. Theoretical analysis shows that this learning objective produces a step-wise reward function learned from trajectory preferences. Then the implicit step rewards are used to compute step-level advantages, which are combined with trajectory (or episode)-level advantages for policy updates, creating a self-reinforcing training loop. We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA. Crucially, our method shows superior performance over frontier LLMs and strong RL baselines across domains, achieving state-of-the-art results with higher sample-efficiency and training stability. Further analysis also demonstrates efficient exploration by **iStar** with increased rewards in both step- and episode-level while maintaining fewer steps to achieve task success.

Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order sampling, performance is highly sensitive to the choice of which position to unmask next. Prior work typically relies on rule-based schedules (e.g., max-confidence, max-margin), which provide ad hoc improvements. In contrast, we replace these heuristics with a learned scheduler. Specifically, we cast denoising as a KL–regularized Markov decision process (MDP) with an explicit reference policy and optimize a regularized objective that admits policy-improvement and convergence guarantees under standard assumptions. We prove that the optimized policy under this framework generates samples that more closely match the data distribution than heuristic schedules. Empirically, across four benchmarks, our learned policy consistently outperforms max-confidence: for example, on SUDOKU, where unmasking order is critical, it yields a 22% gain over random and a 12% gain over max-confidence.

Recent years have seen rigorous proofs of quantum advantages in machine learning, particularly when data is labeled by cryptographic or inherently quantum functions. These results typically rely on the infeasibility of classical polynomial-sized circuits to evaluate the true labeling function. While broad in scope, these results however reveal little about advantages stemming from the actual learning process itself. This motivates the study of the so-called identification task, where the goal is to ``just'' identify the labeling function behind a dataset, making the learning step the only possible source of advantage. The identification task also has natural applications, which we discuss. Yet, such identification advantages remain poorly understood. So far they have only been proven in cryptographic settings by leveraging random-generatability, the ability to efficiently generate labeled data. However, for quantum functions this property is conjectured not to hold, leaving identification advantages unexplored. In this work, we provide the first proofs of identification learning advantages for quantum functions under complexity-theoretic assumptions. Our main result relies on a new proof strategy, allowing us to show that for a broad class of quantum identification tasks there exists an exponential quantum advantage unless BQP is in a low level of the polynomial hierarchy. Along the way we prove a number of more technical results including the aforementioned conjecture that quantum functions are not random generatable (subject to plausible complexity-theoretic assumptions), which shows a new proof strategy was necessary. These findings suggest that for many quantum-related learning tasks, the entire learning process—not just final evaluation—gains significant advantages from quantum computation